Meeting Banner
Abstract #1154

To the point: deep learning on dense T2 point clouds for improved feature extraction

Claudia Iriondo1, Alaleh Razmjoo2, Francesco Caliva2, Sharmila Majumdar2, and Valentina Pedoia2
1Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States, 2University of California, San Francisco, San Francisco, CA, United States

To-the-point (TTP) is a novel approach for analyzing compositional MR imaging data. By representing tibial and femoral cartilage T2 values as a dense point cloud, our approach can leverage the data's inherent sparsity while maintaining local geometric properties, leading to improved feature extraction and faster image processing times. Experiments on the whole OAI T2 dataset show strong performance in an OA diagnosis task 82.44% sens, 82.59% spec, with extracted features even identifying patients who would become diagnosed with OA 1 to 2 years in the future.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords